© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 84356
    Prev
    Next
    INDEX
    Explanations

    academic journals and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     since
    -1.16
     many
    -1.13
     several
    -1.12
    Tomo
    -1.05
     other
    -1.05
    ↵↵
    -1.05
     there
    -1.05
     statunit
    -1.03
     first
    -1.03
     this
    -1.03
    POSITIVE LOGITS
    still
    1.10
    必要があります
    1.09
    
    1.08
    possibly
    1.07
    gré
    1.05
     italiens
    1.05
    toa
    1.04
     préféré
    1.02
    always
    1.02
    Seriously
    1.02
    Activations Density 0.016%

    No Known Activations